Triple

T6079899
Position Surface form Disambiguated ID Type / Status
Subject Heo Sung-tae E135495 entity
Predicate givenName P17 FINISHED
Object Sung-tae
Sung-tae is a Korean masculine given name commonly used in South Korea.
E591667 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Sung-tae | Statement: [Heo Sung-tae, givenName, Sung-tae]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sung-tae
Context triple: [Heo Sung-tae, givenName, Sung-tae]
  • A. Jang Deok-su
    Jang Deok-su is a brutal, debt-ridden gangster who serves as one of the primary antagonists in the South Korean survival drama series "Squid Game."
  • B. Suh Yun-bok
    Suh Yun-bok was a South Korean long-distance runner best known for winning the 1947 Boston Marathon and later serving as a symbolic sports figure in Korea.
  • C. Cho Sang-woo
    Cho Sang-woo is a central character in the South Korean series "Squid Game," portrayed as a once-successful investment banker whose desperation and moral decline drive much of the show's tension and drama.
  • D. Chung Sun-man
    Chung Sun-man is a South Korean athlete best known for lighting the Olympic cauldron at the opening ceremony of the 1988 Seoul Summer Olympics.
  • E. O Yeong-su
    O Yeong-su is a veteran South Korean actor best known internationally for his acclaimed performance as the elderly contestant Oh Il-nam in the Netflix series "Squid Game."
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Sung-tae
Triple: [Heo Sung-tae, givenName, Sung-tae]
Generated description
Sung-tae is a Korean masculine given name commonly used in South Korea.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sung-tae
Target entity description: Sung-tae is a Korean masculine given name commonly used in South Korea.
  • A. Jang Deok-su
    Jang Deok-su is a brutal, debt-ridden gangster who serves as one of the primary antagonists in the South Korean survival drama series "Squid Game."
  • B. Suh Yun-bok
    Suh Yun-bok was a South Korean long-distance runner best known for winning the 1947 Boston Marathon and later serving as a symbolic sports figure in Korea.
  • C. Cho Sang-woo
    Cho Sang-woo is a central character in the South Korean series "Squid Game," portrayed as a once-successful investment banker whose desperation and moral decline drive much of the show's tension and drama.
  • D. Chung Sun-man
    Chung Sun-man is a South Korean athlete best known for lighting the Olympic cauldron at the opening ceremony of the 1988 Seoul Summer Olympics.
  • E. O Yeong-su
    O Yeong-su is a veteran South Korean actor best known internationally for his acclaimed performance as the elderly contestant Oh Il-nam in the Netflix series "Squid Game."
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69c0087ad31c8190ab936e0ff28614b6 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c0577209b88190afe5b1365cf6436d completed March 22, 2026, 8:56 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6409d48408190b2048c07272277ac completed March 27, 2026, 8:32 a.m.
NEDg Description generation batch_69c6421cfa948190b62735451ede82f0 completed March 27, 2026, 8:38 a.m.
NED2 Entity disambiguation (via description) batch_69c6426f194c819086fa4baffe8d237b completed March 27, 2026, 8:40 a.m.
Created at: March 22, 2026, 4:11 p.m.